Study: MRI Could Predict Response to Antidepressants

A recent study found that functional magnetic resonance imaging (fMRI) may predict treatment response in patients with major depressive disorder.

According to researchers, predicting treatment response may be beneficial for addressing current strains in the health care system by reducing the number of treatments and time to remission in patients.
___________________________________________________________________________________________________________________________________
RELATED CONTENT
Are Antidepressant Side Effects More Common in Patients with Depression and Panic Disorder? 
Smoking Cessation Could Improve Depression Symptoms
___________________________________________________________________________________________________________________________________

In their trial, researchers used neural and performance predictors during a cognitive control task to predict treatment response in 36 patients. Fourteen participants received duloxetine, and 22 received escitalopram for 10 weeks. Participants completed the Hamilton Depression Rating Scale before and after treatment.

Researchers used fMRI and performance during a Parametric Go/No-go test to predict percent changes in the Hamilton Depression Rating Scale after treatment.

They determined that hemodynamic response function-based contrasts and task-related independent components were predictors for treatment response.

“Independent components analysis component beta weights and hemodynamic response function modelling activation during Commission errors in the rostral and dorsal anterior cingulate, mid-cingulate, dorsomedial prefrontal cortex, and lateral orbital frontal cortex predicted treatment response,” the researchers wrote.

Likewise, more errors on tasks predicted better treatment response in patients.

A regression model showed that independent component analysis, hemodynamic response function-modelled, and performance measures had a 90% accuracy for predicting treatment response. Clinical features alone had a 74% accuracy in predicting treatment response.

“The strong link to a task paradigm provided by use of independent component analysis is a potential breakthrough that can inform ways in which prediction models can be integrated for use in clinical and experimental medicine studies,” the researchers concluded.

—Melissa Weiss

Reference:

Crane NA, Jenkins LM, Bhaumik R, et al. Multidimensional prediction of treatment response to antidepressants with cognitive control and functional MRI [published online January 24, 2017]. Brain. doi:10.1093/brain/aww326.